Optimizing Policymakers’ Loss Functions in Crisis Prediction: Before, Within or After?
Peter Sarlin, Gregor von Schweinitz
Macroeconomic Dynamics,
Nr. 1,
2021
Abstract
Recurring financial instabilities have led policymakers to rely on early-warning models to signal financial vulnerabilities. These models rely on ex-post optimization of signaling thresholds on crisis probabilities accounting for preferences between forecast errors, but come with the crucial drawback of unstable thresholds in recursive estimations. We propose two alternatives for threshold setting with similar or better out-of-sample performance: (i) including preferences in the estimation itself and (ii) setting thresholds ex-ante according to preferences only. Given probabilistic model output, it is intuitive that a decision rule is independent of the data or model specification, as thresholds on probabilities represent a willingness to issue a false alarm vis-à-vis missing a crisis. We provide real-world and simulation evidence that this simplification results in stable thresholds, while keeping or improving on out-of-sample performance. Our solution is not restricted to binary-choice models, but directly transferable to the signaling approach and all probabilistic early-warning models.
Artikel Lesen
Optimizing Policymakers' Loss Functions in Crisis Prediction: Before, Within or After?
Peter Sarlin, Gregor von Schweinitz
Abstract
Early-warning models most commonly optimize signaling thresholds on crisis probabilities. The expost threshold optimization is based upon a loss function accounting for preferences between forecast errors, but comes with two crucial drawbacks: unstable thresholds in recursive estimations and an in-sample overfit at the expense of out-of-sample performance. We propose two alternatives for threshold setting: (i) including preferences in the estimation itself and (ii) setting thresholds ex-ante according to preferences only. Given probabilistic model output, it is intuitive that a decision rule is independent of the data or model specification, as thresholds on probabilities represent a willingness to issue a false alarm vis-à-vis missing a crisis. We provide simulated and real-world evidence that this simplification results in stable thresholds and improves out-of-sample performance. Our solution is not restricted to binary-choice models, but directly transferable to the signaling approach and all probabilistic early-warning models.
Artikel Lesen
Optimizing Policymakers' Loss Functions in Crisis Prediction: Before, Within or After?
Peter Sarlin, Gregor von Schweinitz
Abstract
Early-warning models most commonly optimize signaling thresholds on crisis probabilities. The ex-post threshold optimization is based upon a loss function accounting for preferences between forecast errors, but comes with two crucial drawbacks: unstable thresholds in recursive estimations and an in-sample overfit at the expense of out-of-sample performance. We propose two alternatives for threshold setting: (i) including preferences in the estimation itself and (ii) setting thresholds ex-ante according to preferences only. We provide simulated and real-world evidence that this simplification results in stable thresholds and improves out-of-sample performance. Our solution is not restricted to binary-choice models, but directly transferable to the signaling approach and all probabilistic early-warning models.
Artikel Lesen
The Impact of Preferences on Early Warning Systems - The Case of the European Commission's Scoreboard
Tobias Knedlik
European Journal of Political Economy,
2014
Abstract
The European Commission’s Scoreboard of Macroeconomic Imbalances is a rare case of a publicly released early warning system. It allows the preferences of the politicians involved to be analysed with regard to the two potential errors of an early warning system – missing a crisis and issuing a false alarm. These preferences might differ with the institutional setting. Such an analysis is done for the first time in this article for early warning systems in general by using a standard signals approach, including a preference-based optimisation approach, to set thresholds. It is shown that, in general, the thresholds of the Commission’s Scoreboard are set low (resulting in more alarm signals), as compared to a neutral stand. Based on political economy considerations the result could have been expected.
Artikel Lesen
Determinants of employment - the macroeconomic view
Christian Dreger, Heinz P. Galler, Ulrich (eds) Walwai
Schriften des IWH,
Nr. 22,
2005
Abstract
The weak performance of the German labour market over the past years has led to a significant unemployment problem. Currently, on average 4.5 mio. people are without a job contract, and a large part of them are long-term unemployed. A longer period of unemployment reduces their employability and aggravates the problem of social exclusion.
The factors driving the evolution of employment have been recently discussed on the workshop Determinanten der Beschäftigung – die makroökonomische Sicht organized jointly by the IAB, Nuremberg, and the IWH, Halle. The present volume contains the papers and proceedings to the policy oriented workshop held in November 2004, 15-16th. The main focus of the contributions is twofold. First, macroeconomic conditions to stimulate output and employment are considered. Second, the impacts of the increasing tax wedge between labour costs and the take home pay are emphasized. In particular, the role of the contributions to the social security system is investigated.
In his introductory address, Ulrich Walwei (IAB) links the unemployment experience to the modest path of economic growth in Germany. In addition, the low employment intensity of GDP growth and the temporary standstill of the convergence process of the East German economy have contributed to the weak labour market performance. In his analysis, Gebhard Flaig (ifo Institute, München) stresses the importance of relative factor price developments. A higher rate of wage growth leads to a decrease of the employment intensity of production, and correspondingly to an increase of the threshold of employment. Christian Dreger (IWH) discusses the relevance of labour market institutions like employment protection legislation and the structure of the wage bargaining process on the labour market outcome. Compared to the current setting, policies should try to introduce more flexibility in labour markets to improve the employment record. The impact of interest rate shocks on production is examined by the paper of Boris Hofmann (Deutsche Bundesbank, Frankfurt). According to the empirical evidence, monetary policy cannot explain the modest economic performance in Germany. György Barabas and Roland Döhrn (RWI Essen) have simulated the effects of a world trade shock on output and employment. The relationships have been fairly stable over the past years, even in light of the increasing globalization. Income and employment effects of the German tax reform in 2000 are discussed by Peter Haan and Viktor Steiner (DIW Berlin). On the base of a microsimulation model, household gains are determined. Also, a positive relationship between wages and labour supply can be established. Michael Feil und Gerd Zika (IAB) have examined the employment effects of a reduction of the contribution rates to the social security system. To obtain robust results, the analysis is done under alternative financing scenarios and with different macroeconometric models. The impacts of allowances of social security contributions on the incentives to work are discussed by Wolfgang Meister and Wolfgang Ochel (ifo München). According to their study, willingness to work is expected to increase especially at the lower end of the income distribution. The implied loss of contributions could be financed by higher taxes.
Artikel Lesen
